ATLANTIS – Indoor Planning with Augmented and Diminished Reality Werner Bailer, Georg Thallinger DIGITAL, JOANNEUM RESEARCH Graz, Austria {firstname.lastname}@joanneum.at Vasileios Gkitsas, Petros Drakoulis, Antonis Karakottas, Dimitrios Pattas, Dimitris Zarpalas ITI, Centre for Research and Technology Hellas Thessaloniki, Greece {gkitsasv, petros.drakoulis, ankarako, dim.pattas, zarpalas}@iti.gr Brita Piovesan, Robert Huemer Roomle GmbH Linz, Austria {firstname.lastname}@roomle.com Richard Whitehand, Per Str¨ om Usability Partners Stockholm, Sweden {firstname.lastname}@usabilitypartners.se Abstract—The H2020 ATLANTIS project (2020-2022) creates an augmented reality (AR) tool for indoor planning. The tool uses artificial intelligence (AI) services for scene understanding, enabling planning from a single panorama. Diminished reality (DR) is used to conceal real-world objects that would conflict with newly inserted virtual ones. Index Terms—augmented reality, indoor planning, user- centred design, scene understanding I. I NTRODUCTION A. Motivation Visualizing and communicating ideas is a key issue in applications like interior design, furniture retailing or reno- vation, which involves interaction between professionals (e.g., designers, sales staff) and consumers/future users. Making this communication process effective saves costs, avoids later mod- ifications, and results in providing tailored solutions and higher customer satisfaction. Experts usually express their ideas in traditional 2D drawings produced by computer aided design (CAD) software, making it difficult for the consumers to comprehend them. Emerging technologies such as augmented reality (AR) have the potential to make this process more effective, and put consumers in a better position to review options by experts, or express their ideas, directly in the target environment. Complementing AR with virtual reality (VR) enables visualizing planned scenes both on and off site, i.e., consumers can view overlays over real environments, while the virtual scene can be edited by professionals in the office. While a number of AR indoor planning apps already exist (for pointers to many of them see [1]), there are two main issues that are not yet satisfactorily addressed: First, creation of the room layout needs to be done manually in most apps, or via importing a CAD model. This requires some IT and technical skills, and may be an obstacle for users. Second, indoor design The research leading to these results has received funding from the Euro- pean Union’s Horizon 2020 research and innovation programme under grant agreement no. 951900 ATLANTIS (“Authoring tool for indoor augmented and diminished reality experiences” (https://atlantis-ar.eu). does in many cases not start from scratch in an empty room, but makes changes to an existing room. When viewing changes on site, the realism of AR is severely degraded when the overlaid 3D objects added to the scene clash with real objects. B. Concept The first issue can be addressed by simplifying the capture process, requiring only a single panoramic image. Extracting semantic information about the room from this image is en- abled by automation. Recent advances in artificial intelligence (AI)-based visual scene understanding enable this automation for constrained environments (such as private or office indoor scenes). These technologies enable detecting the layout of the captured room as well as objects present there, and their boundaries and dimensions. Merging the roles of user and creator also blurs the line between authoring and consuming an AR/VR scene, which are currently often done in separate tools. The second issue can be addressed by diminished reality (DR) technologies, which enable visually concealing real objects, a functionality not yet widely found in AR apps. ATLANTIS brings together two SMEs (Roomle, UP), one providing the mobile app and backend and data, the other focusing on UX design and evaluation, and two research organisations (JOANNEUM RESEARCH, CERTH), develop- ing AI services for scene understanding, reconstruction and inpainting. C. User-centred design approach ATLANTIS addresses two main target user categories: (1) Professionals working in interior design and (2) consumers improving their homes. Users in category 1 are professionals working with selling home or office furnishings, those working with selling/renting private or commercial properties, and in- terior designers assisting either professional clients (e.g. archi- tects, estate agents) or consumers (e.g. homeowners/renters). Users in category 2 are those redecorating/renovating their homes and/or looking to buy new furniture.